International Journal of Engineering and Technical Research (IJETR)
ISSN: 2321-0869, Volume-2, Issue-8, August 2014
A Prominent Application for Wild Identification,
Segmentation and Tracking
Chhatra Pal Singh , Sanjay Kumar
Abstract In now a days wild tiger often killed people. In
India, over 50 to 60 people are killed by tiger every year and this
rate is growing year by year. The proposed work is to develop a
Prominent Application for security level application that is
could be used by forest department. This security level
application segment, identified and tracking the tiger Object.
The security level system contain four main major parts segment
the tiger object, identification of tiger object, track the tiger
object and calculate the distance traveled by the target tiger
object from starting position to the suspected boundary. If tiger
pass out the coordinate of suspected boundary then generate a
message tiger goes outside the boundary.
Index Terms Object Identification, Image
Segmentation wild tracking Method. Feature matching
I. INTRODUCTION
Image Processing is a technique to translate an image into
digital figure and carry out some operations to get a better
image and take out useful information from it [1]. In this
research work the concept of the segmentation and
identification of tiger object movement to trigger warning. In
todays time tiger often kill people. A total no. of 3,73,000
people were killed by Tigers from 1800 2009 . in South and
Southeast Asia. In India, 50 to 60 people are killed by tiger
each year and this rate is growing year by year. The proposed
work is to develop a security level application that is could be
used by forest department. This security level application
identified and tracking the special object (Tiger) and object
passes outside the boundary of forest then send the message or
trigger warning to the related forest ranger. This application is
useful prevent the attack on the humans by tiger in future
aspect. In this dissertation, we have to find the better result of
segmentation using Fixed Region Technique based on
continuous edges corresponding to earlier segmentation
technique based on discontinuous of edges. In this
dissertation we have to identify the tiger in images using old
Interest Point Matching and new purposed Putatively
Feature Matching Technique and
then tracking the tiger in video with the help of purposed
Point Change over Technique. This tracking technique
applied on sequence of tiger images or video. In this
correspondence if tiger goes outside the suspected forest
boundary means if tiger tracking coordinate is greater than
suspected boundary coordinate then a message would be sent
Manuscript received August 23, 2014.
Chhatra Pal Singh , Department of Computer Science & Engineering,
Uttarakhand Technical University, Dehradun, India, 9837979258.
Sanjay Kumar, Assistant Professor in Department of Computer Science
& Engineering, Uttarakhand Technical University, Dehradun, India,
9412148830.
159
to the forest ranger so that appropriate action can be taken
timely. In this dissertation find the total distance between the
starting position of object and the suspected boundary using
Coordinate Distance Technique. In this technique find the
initial position of target object in each image in terms of x and
y coordinate. Calculate the change between first target object
position and second target object position using Euclidean
Distance formula and this process continue to the suspected
boundary position then add each change and find out the
distance travelled by object from starting point to suspected
boundary.
Image processing edge detection is basic tool used. Mostly
image processing application s to obtain information from the
frames as precursor step to feature extraction and object
segmentation. It is a simple process which detects boundaries
between object and back ground in an image. edge detection
can also be used which improve the appearance of blurred
image. Segmentation is the foundation of object recognition
and computer vision [2][3].
II. LITERATURE SERVEY
A. Literature Survey
In this paper, we used seven techniques for edge
detection, Sobel operator technique, Prewitt technique,
Kiresh technique, Laplacian technique; canny technique,
Robertss technique and Edge Maximization Technique
(EMT) and they are compared with one another so as to
choose the best technique for edge detection segment image.
These techniques applied on one satellite images to choose
base guesses for segmentation or edge detection image.
Discontinuity detection is partition an image based on abrupt
changes in gray-level image. Canny technique is very
important method to find edges by isolating noise from the
image before find edges of image, without affecting the
features of the edges in the image and then applying the
tendency to find the edges and the critical value for threshold
[1].
In this paper define the two ways of edge detection technique
that are gradient and Laplacian. The gradient method detects
the edges by looking for the maximum and minimum in the
first derivative of the image. The Laplacian method searches
for the zero crossings in the second derivative of the image to
find edges. In Laplacian of Gaussian edge detection uses three
steps in its process. The First one is filter which is the image
object. Secondly, it enhances the image object and finally
detects [3].
In this paper, we identify the multiple objectives associated
with image segmentation problems of natural images. The
main aim of paper to provide the implementation of for edge
www.erpublication.org
 A Prominent Application for Wild Identification, Segmentation and Tracking
detection technique like Robert Edge Detection, Prewitt Edge
Detection, and Log Edge Detection, Sobel Edge Detection for
natural image segmentation and their comparisons. In this
paper define Edge detection techniques are classified in two
categories: parallel and sequential techniques. The parallel
edge detection technique implies that the decision of whether
a set of points are on an edge or not is dependent on the gray
level of the set and some set of its neighbors, which includes
high emphasis spatial frequency filtering, gradient operators,
adaptive local operator, relaxation, and line and curve fitting,
while the sequential edge detection techniques make decision
based on the results of the previously examined points [4].
In this paper define the Object identification is to identify an
object which belongs to and feature extraction to extract
features from the image like size, shape, texture and spectral
information of the image. With the help of feature extraction
techniques we can easily find the relevant information from
the data and the data can easily be classified. There are several
existing techniques for object identification and feature
extraction which are discussed in this paper. The aim of this
paper is to represent an approach for extracting the knowledge
from the image. Identification means to identify the objects
which belong to an image because of noise and shadow
objects cannot be identified. Object recognition or
identification can be classified in two types based on the
feature type they use. The two types are edge based and patch
based feature type. Edge based feature type extracts the edge
map of an image and identify the features of the object at the
edges. It represents the object boundaries and data efficiently.
Patch based feature type uses appearance as cues [27].
In this paper define the kernel based object tracking using
color histogram technique has been applied for different
challenging situations. Every tracking method requires an
object detection mechanism either in every frame or when the
object first appears in the video. Some commonly used object
detection methods are: point detectors, background
subtraction, segmentation and supervised learning. After
detection of the object the trackers task is to generate the
trajectory of an object over time by locating the object
position in every frame of the video [31].
B. Application of Image Segmentation
1. Object detection
Pedestrian detection
Face detection
Brake light detection
2. Medical
Surgery planning
Virtual surgery simulation
Intra-surgery navigation
3. Traffic control systems
160
III. OBJECT SEGMENTATION, IDENTIFICATION
AND TRACKING
A. Image Segmentation
Image segmentation is to partition an image into meaningful
regions with respect to a particular application. The analysis
of image objects begin with finding them-judge which object
belong to related pixel values. This is known as image
segmentation, the technique of extracting objects from the
background in an image. Segmentation is the approach of
separating a image into its meaningful parts or regions or
object.
B. Types of Image Segmentation
There are two types of image segmentation
a. Edge based segmentation
In image processing edge may be simplify as a group of
connected pixels that belong to boundary between from one
regions to other. Basically, edge detection is a method of
segmentation which is extract an image into discontinuity
region. This method plays an vital role in image processing
system and usual aspects of our real world life.The process of
detecting and locating intense changes of discontinuities in
an image . In image processing for a noisy image it is hard to
find edges as both noise and edge contains maximum
frequency contents which outcome in distorted and blurred
result. In this paper we analyse lot of edge detection
techniques as Robert, Canny and Sobel method. The edge
detection makes use of lot of operators to find changes in the
gradients of the grey scale images. The edge widely exists
between objects and background, objects and primitives. It
contains rich information, step property, shape etc, which is
able to describe the target object.
Figure 1: Edge Based Segmentation [35]
b. Thresholding based segmentation
Thresholding is probably the most frequently used technique
to segment an image. The grayscale image (also referred as
intensity images) can be converted to binary image by a
process called thresholding. The histogram thresholding
technique is used to segment an image.
www.erpublication.org
 International Journal of Engineering and Technical Research (IJETR)
ISSN: 2321-0869, Volume-2, Issue-8, August 2014
D. Object Tracking
Object tracking is the approach of locating object when
moving over time in an image sequence. It has a variety of
uses, some of which are: human-computer interaction,
security and surveillance, video communication and
compression, augmented reality, traffic control, medical
imaging and video editing. Video tracking can be a time
consuming process due to the amount of data that is contained
in video.

Figure 2 Thresholding Based Segmentation IV. PROPOSED WORK USING MAT LAB
In our proposed work we used fix region for segmentation
C. Object Identification returns edges of the selected object and another is it returns
edges at those point where gradient of image is low and high
intensity and gives better segmentation result. In object
In image processing object identification is the method of
identification we used the putatively feature matching
seeking a given target object in an image sequence or video.
techniques in this techniques find the corner and surface
In an image any object, there are lot off 'features' which are
feature of object. Surface feature is presented in region of
strongest points on the object that can be extracted to produce
object it returns low intensity and high intensity feature both
a "feature" detail of the object. This detail extracted from a
surface and corner. So detection is more successful.
training target image can then be used to detect the object
when try to locate the target object in a test entire image
containing other objects

Figure: 4: Masking The Image Using Fixed Region

Technique
Figure 3: object identification

a. Technique of Object identification

b. Template matching
Template matching is a approach for seeking mini parts of an
image which match a sample template target image. Template
matching is a straightforward process. In this technique
template images for different objects are stored. When an
image is given as input to the system, it is matched with the
stored template images to determine the object in the input
image. Templates are frequently used for recognition of
characters, numbers, objects, etc. It can be performed on
either color or gray level images. Template matching can
either be pixel to pixel matching or feature based. In feature
based the features of template image is compared to
c. Color based matching Figure 5: Segment The Image Using Fixed Region Technique

Color provides potent information for object recognition. A A. Results of Point Change Over Tracking Technique
simple and efficient object detection scheme is to represent In this technique track the tiger object in each frame on X and
and match images on the basis of color histograms. Y coordinate movement. X and Y coordinate move on the

161 www.erpublication.org
 A Prominent Application for Wild Identification, Segmentation and Tracking

color density feature of crop target tiger image and source

tiger object in the frame to frame. When match the similar
color density feature of target tiger object with respect to
source tiger image frame to frame then get the x and y
coordinate of source tiger object in each frame and track the
tiger on the basis of x and y coordinate

Figure 6: Track the Tiger in each Frame using Color Density

Feature
Figure 9 Proposed Feature Matching
B. Results of Coordinate Distance Technique Technique

In this technique find the distance from starting position of

object to suspected boundary.

Figure 7 Starting Coordinate Point of Target Object and

Suspected Boundary

Figure 8 Distance Between First Tiger Position and

Suspected Boundary
Figure 10 Proposed Point Change over Technique

162 www.erpublication.org
 International Journal of Engineering and Technical Research (IJETR)
ISSN: 2321-0869, Volume-2, Issue-8, August 2014
V. APPLICATION OF EMAGE PROCESSING
Security: Demising image in order to identify a crime
suspect whose picture was taken by either a poor
camera or in a poor condition [9].

Medicine: To clean image in order to have a clear

understanding of the part of the body that was
snapped (e.g. X-rays) [9]. Mr. Chhatra Pal Singh, Chhatra Pal Singh is a
Graduate in Computer Science and Engineering From IEC College of
Engineering and Technology Greater Noida which is affiliated to Gautam
Astronomical Aplication: Image taken from space Budh Technical University Formally (UPTU) 2012. Presently he is pursuing
by satellites [9]. Master of Technology in Computer Science and Engineering from
Uttarakhand Technical University Dehradun. His Area of interest Image
Processing, Computer Network and Data Mining.
VI. CONCLUSION
In this paper, we conclude that image identification,
segmentation is a very important technique which is used in
digital image processing. This Project focuses mainly on the
segmentation and identification of Special Object Tiger. The
interaction between image segmentation and object
recognition in the framework of the Sobel, Prewitt, Roberts,
Canny are studied and build new own Technique for better
result in future. It provides information for identification or Mr. Sanjay Kumar, currently working as a
recognition and interpretation of object. In our work find the assistant professor in Uttarakhand Technical University, Dehradun. Done
his Masters degree from Indian Institute of Science Bangalore in
distance from starting position of object to suspected ComputerScience & Automation Department. His current
boundary. workingonSecurity in Wireless Sensor Networks. Doing PhD from
Uttarakhand Technical university
REFERENCES

[1]-Saiful Islam, Majidul Ahmed, A Study on Edge Detection Techniques

for Natural Image Segmentation, International Journal of Innovative
Technology and Exploring Engineering (IJITEE)
,ISSN:2278-3075,Volume-2,Issue-3,Februrary 2013.
[2]-Mr.Salem Saleh Al-amri, Dr.N.V.Kalyankar, Dr.Khamitkar S.D,Image
Segmentation By Using Edge Detection. Journal on Computer
Science and Engineering,and Vol.02,No.03 ,2010,804-807.
[3]-Y.Ramadevi,T.Sridevi,B.Poornima,B.Kalyani, and Object
Recognition Using Edge Detection Technique, International Journal
Of Computer Science & Information Technology,Vol 2,No 6,December
2010
[4]- Mr. Salem Saleh Al-amri, Dr. N. V Kalyankar, Dr. Khamitkar, Image
Segmentation by using Edge detection, International Journal on
Computer Science and Engineering, Vol. 02, No. 03, 2010

[5]-G. T Shrivakshan, Dr. C. Chandrasekar, A Comparison of various Edge

Detection Techniques used in Image Processing, International Journal
of Computer Science Issues, Vol.9,Issues 5,No 1, September 2012

[6]-Saiful Islam, Majidul Ahmed, A Study on Edge Detection Techniques

for Natural Image Segmentation, International Journal of Innovative
Technology and Exploring Engineering (IJITEE), ISSN: 2278-3075,
Volume-2, Issue-3, February 2013

[7]- Navjeet, Simarjeet Kaur, Object Identification and Feature Extraction

Technique of a Satellite Data:A Review, International Journal of
Computer Engineering and Applications, Volume 6, Issue 2, May 14
[8.] Prajna ParimitaDash, Dipti patra, Sudhansu Kumar Mishra, Jagannath
Sethi, Kernel based Object Tracking using Color Histogram
Technique, International Journal of Electronics and Electrical
Engineering, Volume 2 Issue 4 April 2012

[9] Edge Based Segmentation,

ttp://www.mathworks.in/discovery/edge-detection.html

163 www.erpublication.org